IBNS-Based Pattern-Based DDoS Detection Using Neural Networks and Reinforcement Learning
Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
As current network infrastructures grow in complexity and size, cybersecurity risks such as Distributed Denial-of-Service (DDoS) attacks have evolved to be increasingly sophisticated and difficult to counteract. DDoS attacks exploit network weaknesses by inundating systems with malicious traffic, therefore disrupting services and causing significant operational and financial losses. Static rule-based algorithms, commonly employed in conventional DDoS detection systems, are incapable of adapting to evolving attack patterns. Artificial intelligence (AI) techniques such as neural networks (NNs) and reinforcement learning (RL), offers an effective solution by enabling dynamic and intelligent threat detection. Intent-Based Networking (IBN) is a novel framework that automates network administration by converting overarching business objectives into system settings. IBN security features can be further improved when combined with Pattern Based DDoS Detection, which allows real-time attack detection and mitigation. Neural networks can discern between valid and invalid HTTP traffic through deep learning techniques in massive datasets. Adaptive threat management is possible through persistent network activity learning, making it possible to continually modify and optimize the response strategies to threats. In this paper, a new approach for defending against TCP SYN based DDoS attacks is presented through the fusion of machine learning, reinforcement learning, and intent based networking. While reaction time is enhanced by 43% with RL-based mitigation, the proposed model achieves 99.86% accuracy utilizing ML. The system enhances network protection by adapting security regulations, utilizing up-to-date threat intelligence, and monitoring activity in real-time. Indices of the IBNS architecture improve not only lessen the rate of false positive results 0.0008 FPR, stabilize the network, but also shift into proactive mode engagement to neutralize risks. This innovation strengthens the cybersecurity infrastructure of an institution by reducing the intervention of humans in the detection and tracking of dynamic cycle attacks.